An adaptive image segmentation algorithm for natural scene images based on probabilistic neural networks

Considering the problem of automatic objects detection in natural scene images, a new adaptive image segmentation algorithm for natural scene images based on probabilistic neural networks (PNN) is proposed in this paper. The probabilistic neural networks used for image segmentation is designed in this algorithm. Its input vector consists of image global color features computed by the statistics theory and pixel's gray-values in R, G and B color channels. Its output vector is the binary vector including four elements, and the element with value 1 represents recognized color category. This neural network can divide all pixels of one color image into four types as yellow, red, blue and others. Then the color image will be segmented to the binary image corresponding to given color. To verify the validity of proposed algorithm, it is applied to many natural scene images. Experimental results show the algorithm can efficiently segment object regions of specific colors from color images, and is more adaptable and reliable to natural lighting conditions. The proposed algorithm has important application value in object detection and recognition from natural scene images.

[1]  Xuchao Li,et al.  Wavelet domain possibilistic c-means clustering based on Markov random field for image segmentation , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[2]  P. Lombardo,et al.  Segmentation-based technique for ship detection in SAR images , 2001 .

[3]  Jaroslav Poÿ.  Functional Transforms in MR Image Segmentation , 2008 .

[4]  Jesmin F. Khan,et al.  Image segmentation based road sign detection , 2009, IEEE Southeastcon 2009.

[5]  Korris Fu-Lai Chung,et al.  A novel image thresholding method based on Parzen window estimate , 2008, Pattern Recognit..

[6]  Azriel Rosenfeld,et al.  Image Processing and Recognition , 1979, Adv. Comput..

[7]  Lorenzo Bruzzone,et al.  Image thresholding based on the EM algorithm and the generalized Gaussian distribution , 2007, Pattern Recognit..

[8]  Tianxu Zhang,et al.  Knowledge-based adaptive thresholding segmentation of digital subtraction angiography images , 2007, Image Vis. Comput..

[9]  Bir Bhanu,et al.  Symmetry integrated region-based image segmentation , 2009, CVPR.

[10]  Anil K. Jain,et al.  A wrapper-based approach to image segmentation and classification , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[11]  M. Benallal,et al.  Real-time color segmentation of road signs , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[12]  Shrikanth S. Narayanan,et al.  Region Segmentation in the Frequency Domain Applied to Upper Airway Real-Time Magnetic Resonance Images , 2009, IEEE Transactions on Medical Imaging.

[13]  Hai Jin,et al.  Color Image Segmentation Based on Mean Shift and Normalized Cuts , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Jeffrey Mark Siskind,et al.  Image Segmentation with Ratio Cut , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Yong Zhang,et al.  A novel image segmentation method based on random walk , 2009, 2009 Asia-Pacific Conference on Computational Intelligence and Industrial Applications (PACIIA).

[16]  Donald F. Specht,et al.  Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification , 1990, IEEE Trans. Neural Networks.